© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 23-TRANSCODER-HP
    7. 23446
    Prev
    Next
    INDEX
    Explanations

    control, determination

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    unded
    -0.27
    nar
    -0.26
     funded
    -0.26
    çļĦèµĦéĩij
    -0.26
    çļĦåŃ©åŃIJ
    -0.26
    forgettable
    -0.26
    -capital
    -0.25
    èµĦæľ¬
    -0.25
    [child
    -0.25
    ivol
    -0.24
    POSITIVE LOGITS
    atrix
    0.31
    大åħ¨
    0.27
    führ
    0.26
     having
    0.26
    衽
    0.25
     compatibility
    0.25
    wis
    0.25
     Selector
    0.25
    otion
    0.24
    Extras
    0.24
    Activations Density 0.003%

    No Known Activations